PDRNN is a modular hybrid RNN-based system for fusing loosely coupled inertial and radio signals to achieve more accurate and robust pedestrian dead reckoning during high-acceleration movements.
Finding structure in time
3 Pith papers cite this work. Polarity classification is still indexing.
3
Pith papers citing it
years
2026 3verdicts
UNVERDICTED 3representative citing papers
The attractor FCM combines Newton's method to locate fixed points with adaptive gradient descent and causal masking to minimize error in a physics-constrained Jacobian FCM.
QAROO combines quantum neural networks, attention mechanisms, and recurrent networks in a reinforcement learning setup to improve online task offloading performance over baselines in dynamic MEC environments.
citing papers explorer
-
PDRNN: Modular Data-driven Pedestrian Dead Reckoning on Loosely Coupled Radio- and Inertial-Signalstreams
PDRNN is a modular hybrid RNN-based system for fusing loosely coupled inertial and radio signals to achieve more accurate and robust pedestrian dead reckoning during high-acceleration movements.
-
Attractor FCM
The attractor FCM combines Newton's method to locate fixed points with adaptive gradient descent and causal masking to minimize error in a physics-constrained Jacobian FCM.
-
QAROO: AI-Driven Online Task Offloading for Energy-Efficient and Sustainable MEC Networks
QAROO combines quantum neural networks, attention mechanisms, and recurrent networks in a reinforcement learning setup to improve online task offloading performance over baselines in dynamic MEC environments.